Fab Automation, Data and Machine Learning

This course delves into the foundational principles and practical applications of automation, data infrastructure, and machine learning within modern semiconductor fabrication facilities. Students will learn how to leverage real-time data for process control, predictive maintenance, and yield enhancement. The curriculum covers smart manufacturing concepts, statistical process control, machine learning algorithms relevant to wafer processing, and the integration of these technologies into a fully automated fab environment. This course prepares students to design and implement advanced automation and data-driven solutions for semiconductor manufacturing challenges.

Course outline

Lectures, virtual labs, and graded assignments — completed in your browser.

01Introduction to Semiconductor Fab Automation and Smart Manufacturinglecture

02Foundations of Fab Automation Systems (AMHS, MCS, MES)lecture

03Data Acquisition and Infrastructure in Semiconductor Manufacturinglecture

04Statistical Process Control (SPC) and Run-to-Run (R2R) Controllecture

05Yield Management and Defect Classification using Datalecture

06Introduction to Machine Learning for Semiconductor Applicationslecture

07Supervised Learning: Regression and Classification for Process Predictionlecture

08Unsupervised Learning: Clustering and Dimensionality Reduction for Anomaly Detectionlecture

09Reinforcement Learning Concepts for Fab Optimizationlecture

10Data Preprocessing, Feature Engineering, and Model Evaluationlecture

11Advanced Process Control (APC) and Predictive Maintenance using MLlecture

12Digital Twin and Simulation Technologies in Semiconductor Fabslecture

13Ethics, Security, and Cloud Integration for Fab ML Solutionslecture

14Future Trends: AI in Fab Operations and Final Project Presentationslecture

Syllabus

This 14-week course is structured with weekly modules, including lectures, readings, and hands-on assignments utilizing industry-standard tools and simulated fab data. Each week will introduce new concepts, followed by practical exercises and case studies to solidify understanding. Students are expected to actively participate in online discussions, complete all assignments by their deadlines, and contribute to a final project applying learned concepts. Collaboration on conceptual aspects is encouraged, but all submitted work must be individual. Academic integrity is paramount, and any instances of plagiarism or cheating will result in severe penalties. Regular engagement and self-directed learning are essential for success in this online technical program.